Presenter:

Tyler Benster, Julia Gong, Jerry Meng, John Mern, Megumi Sano and Paul Warren will be reviewing Oriol Vinyal's presentation from 2018, focusing on the following three papers:

  1. Learning model-based planning from scratch [2] [John, Tyler]

  2. Imagination-Augmented Agents for Deep Reinforcement Learning [3] [Julia, Meg]

  3. Learning to Search with Monte Carlo Tree Search (MCTS) networks [1] [Jerry, Paul]

These three papers are the assigned readings for class and you might also want to look through Oriol's slides following the link above to get the maximum out of class.

References:

[1]   Arthur Guez, Théophane Weber, Ioannis Antonoglou, Karen Simonyan, Oriol Vinyals, Daan Wierstra, Rémi Munos, and David Silver. Learning to search with MCTSnets. CoRR, arXiv:1802.04697, 2018.

[2]   Razvan Pascanu, Yujia Li, Oriol Vinyals, Nicolas Heess, Lars Buesing, Sébastien Racanière, David P. Reichert, Theophane Weber, Daan Wierstra, and Peter Battaglia. Learning model-based planning from scratch. CoRR, arXiv:1707.06170, 2017.

[3]   Theophane Weber, Sébastien Racanière, David P. Reichert, Lars Buesing, Arthur Guez, Danilo Jimenez Rezende, Adrià Puigdomènech Badia, Oriol Vinyals, Nicolas Heess, Yujia Li, Razvan Pascanu, Peter Battaglia, David Silver, and Daan Wierstra. Imagination-augmented agents for deep reinforcement learning. CoRR, arXiv:1707.06203, 2017.